© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 12477
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports and competition

    oai_token-act-pair · gpt-3.5-turbo

    references to strategy and planning in competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •GPT2 Layer 8 Movie Sentiment Features

    No Comments

    Negative Logits
     PBS
    -0.75
     Journals
    -0.75
    MIT
    -0.73
     UNESCO
    -0.73
     NPR
    -0.72
     Smithsonian
    -0.72
     Funding
    -0.69
     Advertising
    -0.67
     Parents
    -0.65
     Registrar
    -0.65
    POSITIVE LOGITS
     offensively
    1.11
     defensively
    1.06
     synergy
    1.06
     underrated
    1.01
     midfield
    0.99
     versatility
    0.97
     matchup
    0.95
     midrange
    0.93
     combos
    0.93
     clutch
    0.93
    Activations Density 1.243%

    No Known Activations